Artificial Intelligence Agents in Mental Health: A Systematic Review and Meta Analysis
Агенты искусственного интеллекта в охране психического здоровья: систематический обзор и метаанализ
2026-04-22
SCID: 54.1/75mdjrtn
Discuss with AI
large language modelsmental health AI agentsmental health assessmentmultiagent coordinationsystematic review and meta-analysis
Figures from the paper
Abstract (AI)
Abstract The rapid rise of large language models (LLMs) and foundation models has accelerated efforts to build artificial intelligence (AI) agents for mental health assessment, triage, psychotherapy support and clinical decision assistance. Yet a gap persists between healthcare and AI-focused work: while both communities use the language of “agents,” clinical research largely describes monolithic chatbots, whereas AI studies emphasize agentic properties such as autonomous planning, multiagent coordination, tool and database use and integration with multimodal mental health data streams. In this Review, we conduct a systematic analysis of mental health AI agent systems from 2023 to 2025 using a six-dimensional audit framework: (i) system type (base model lineage, interface modality and workflow composition, from rule-based tools to role-aware multi-agent foundation-model systems), (ii) data scope (modalities and provenance, from elicited self-report and chatbot dialogues to electronic health records, biosensing and synthetic corpora), (iii) mental health focus (mapped to ICD-11 diagnostic groupings), (iv) demographics (age strata, geography and sex representation), (v) downstream tasks (screening/triage, clinical decision support, therapeutic interventions, documentation, ethical–legal support and education/simulation) and (vi) evaluation types (automated metrics, language quality benchmarks, safety stress tests, expert review and clinician or patient involvement). Across this corpus, we find that most systems (1) concentrate on depression, anxiety and suicidality, with sparse coverage of severe mental illness, neurocognitive disorders, substance use and complex comorbidity; (2) rely heavily on text-based self-report rather than clinically verified longitudinal data or genuinely multimodal inputs; (3) are implemented as single-agent chatbots powered by general-purpose LLMs rather than role-structured, workflow-integrated pipelines; and (4) are evaluated primarily via offline metrics or vignette-based scenarios, with few prospective, clinician- or patient-in-the-loop studies. At the same time, an emerging class of agentic systems assigns foundation models explicit roles as planners, retrieval agents, safety auditors or supervisors coordinating other models and tools. These multiagent, tool-augmented workflows promise personalization, safety monitoring and greater transparency, but they also introduce new risks around reliability, bias amplification, privacy, regulatory accountability and the blurring of clinical versus non-clinical roles. We conclude by outlining priorities for the next generation of mental health AI agents: clinically grounded, role-aware multi-agent architectures; transparent and privacy-preserving use of clinical and elicited data; demographic and cultural broadening beyond predominantly Western adult samples; and evaluation pipelines that progress from offline benchmarks to longitudinal, real-world studies with routine safety auditing and clear governance of responsibilities between agents and human clinicians.
Key Findings
1
Mental health AI agents rely predominantly on text-based self-report rather than clinically verified longitudinal data or genuinely multimodal inputs.
2
Most systems are single-agent chatbots using general-purpose large language models, rather than role-structured and workflow-integrated multiagent pipelines.
3
Most systems focus on depression, anxiety, and suicidality, while severe mental illness, neurocognitive disorders, substance use, and complex comorbidity receive sparse coverage.
4
The review audits mental health AI agents from 2023–2025 using a six-dimensional framework covering systems, data, diagnoses, demographics, tasks, and evaluation.
5
The review distinguishes clinical chatbot research from AI agent research by emphasizing autonomy, planning, coordination, tool use, database integration, and multimodal data handling as agentic properties.
Research Object
Artificial intelligence agent systems for mental health
Research Subject
Their system architectures, data scopes, mental health coverage, demographic representation, downstream clinical tasks, and evaluation practices
Publication Details
Publication Date
2026-04-22
Journal
Publisher
ISSN
Cited by
0
Access Type
Author Information
Download PDF
Subscribe to digest